Quote:
Originally posted by stocktrader23
"If we go back in history to prior presidential elections, those exit polls were dead on," said Dennis Simon, a political scientist at Southern Methodist University in Dallas. "Something has changed to make them less dead on."
I wonder what it is that changed? ;-)
|
He may be a political scientist but his knowledge of statistics and political history is obviously deficient.
If you don't have a random sample of the population you can have an extremely large error. You really can't even define the error. because they can be systematic.
The 2000 exit polling was replete with error. "Voter News Service" handled the 2000 election. It was said to be a "disaster", "comical" and "a joke". As a result, the networks stopped using them for 2004.
Here's a quick snippet from a 2000 article.
http://baltimore.bizjournals.com/bal...27/daily7.html
"Why the uniformity of (wrong) results? This can be explained by a lack of competition. All of the "competing" major networks are actually colluding with one another, and they call their collusion the Voter News Service. Since they all relied upon the same pooled data, naturally they all made the same error," Lande said.